(26 days)
CardioDay" is a software package that allows a trained physician or health care professional knowledgeable in Holter interpretation, after having performed a long-term continuous electrocardiographic (ECG) recording on digital flash memory Holter recorder, to download and analyze the data from the recorder, review it and produce printed reports.
This device is available only upon the order of a physician or other licensed medical professional and not intended for any ambulatory or home applications.
Federal law restricts CardioDay® to use on order of a physician.
CardioDay is a Holter software which is indicated for patients who may benefit from a long-term continuous electrocardiographic (ECG) recording, but not limited to, those with complaints of palpitations, syncope, chest pain, shortness of breath, or those that need to be monitored to judge their current cardiac functionality such as patients who have recently received pacemakers.
WARNING:
CardioDay® does not perform any diagnosis of data by itself but only displays ECG morphologies and associated, calculated graphs such as heart rate trends, RR variability, and other statistical values.
CardioDay® does not perform any diagnosis of data by itself but only displays ECG morphologies and associated, calculated graphs such as heart rate trends, RR variability, and other statistical values in graphical form. The physician will be able to review, edit, and print the data collected.
CardioDay® is a software package which is delivered on CD.
The provided document is a 510(k) summary for CardioDay®, a Holter ECG software. The submission aims to establish substantial equivalence to a predicate device, Holter for Windows®. The document focuses on comparing the new device against the predicate in terms of various characteristics and functionality, rather than presenting a performance study with specific acceptance criteria and results.
Therefore, many of the requested details about acceptance criteria and a study proving their fulfillment are not explicitly available in the provided text. The document primarily makes a claim of substantial equivalence based on comparison rather than a standalone performance study with defined criteria.
Here's an analysis of the available information:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria or a formal table of device performance metrics against such criteria. Instead, equivalence is established through qualitative comparisons of features and functionalities with the predicate device. The performance is implied to be equivalent to the predicate.
Below is a summary of the comparative analysis, which serves as the basis for claiming "performance":
| Feature Category | Predicate Device (Holter for Windows®) Performance/Characteristic | New Device (CardioDay®) Performance/Characteristic | Equivalence Claim |
|---|---|---|---|
| Intended Use | Holter monitoring software for high-speed data analysis of continuous, long-term ECG, producing printed reports for physician review. Federal law restricts use to physician order. | Software allows trained physician/healthcare professional to download, analyze, review, and produce printed reports from long-term continuous ECG recordings. Available only upon physician order and not for ambulatory/home use. | Substantially Equivalent. The wording is slightly different but the core function and user restrictions are the same. |
| Indications for Use | For patients who benefit from long-term continuous ECG recording, including those with palpitations, syncope, chest pain, shortness of breath, or needing cardiac functionality monitoring (e.g., post-pacemaker). | Same as predicate. | Substantially Equivalent. |
| Device Description | Displays ECG morphologies and associated calculated graphs; physician reviews, edits, and prints data. | Displays ECG morphologies and associated calculated graphs (heart rate trends, RR variability, statistical values); physician reviews, edits, and prints data. Does not perform diagnosis itself. | Substantially Equivalent. Both devices are analysis tools, not diagnostic. |
| Hardware Specs | Pentium II, 32MB RAM, 200MB HDD, VGA 14" display, 1.4MB floppy, Windows 98, parallel port. | Pentium III 500MHz+, 128MB RAM (256MB for XP), 5GB HDD (20GB for 12-lead), 17" CRT/15" TFT XGA display, no floppy required, Windows 98 SE/NT/2000/XP, parallel/USB ports. | Not identical, but determined to have "No influence on safety and effectiveness" as CardioDay®'s requirements "correspond to the current state of the art." |
| Software Features | Broad range including patient data, analysis options (tachycardia, bradycardia thresholds, ST-analysis, pacemaker events), various event detections (VES, VTACH, Pause, etc.), and standard functionalities (start, read, analyze, print). | Broad range including patient data, analysis options, event detections, and standard functionalities. Includes additional editing and printing options not available in the predicate (e.g., "Edit all Beat Labels in a Morphology Bin", more specific printout options). | Substantially Equivalent. Specific differences in editing/printing options are noted but considered to have "No influence on safety and effectiveness." The core analysis modes are the same. |
| Supported Recorders | RZ153+ Digital Recorder, CardioMem® CM 3000 (SMA). | RZ153+ Digital Recorder, CardioMem® CM 3000 (SMA), CardioMem® CM 3000-12. Does not support RZ151 Analog Recorder. | Not identical, but determined to have "No influence on safety and effectiveness." The additional recorder support is seen as an enhancement, and the lack of analog tape recorder support is due to outdated technology. |
| Regulatory Standards | Complies with 21 CFR 820, ISO 9001, IEC 60601-1-4, ANSI/AAMI EC38, IEC 60601-2-47, ISO 14971, EN 980, EN 1041, ISO 15223. | Complies with 21 CFR 820, ISO 9001 / EN 46001 / ISO 13485:2003, IEC 60601-1-4 + A1, ANSI/AAMI EC38, IEC 60601-2-47, ISO 14971 +A1, EN 980, EN 1041, ISO 15223 + AMD1 + AMD2. | Substantially Equivalent. Both devices comply with relevant standards for medical device quality management and safety. |
2. Sample size used for the test set and the data provenance
The document mentions that "The impact of all parameters, especially those specified above, is evaluated with the help of the data bases from American Heart Association (AHA) and Massachusetts Institute of Technology (MIT) and performance evaluations." This indicates that public domain databases (AHA and MIT-BIH Arrhythmia Database are commonly used for Holter analysis algorithm validation) were used for performance evaluations. However, the specific sample size used from these databases for the test set, or details on data provenance (e.g., country of origin, retrospective/prospective) are not specified in this summary.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not provide details on the number or qualifications of experts used to establish ground truth for any test set derived from the AHA or MIT databases. These databases typically come with expert-verified annotations, but this fact is not explicitly stated in relation to this device's validation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not describe any specific adjudication method used for a test set.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
The document does not mention any MRMC study or any study evaluating the improvement of human readers with or without AI assistance. The device is described as a software for trained professionals to review, edit, and print data, explicitly stating that it "does not perform any diagnosis of data by itself." This implies it's an analysis and presentation tool, not an AI-powered diagnostic aid designed to directly assist human readers in improving their diagnostic accuracy.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document notes that performance evaluations used "data bases from American Heart Association (AHA) and Massachusetts Institute of Technology (MIT)." This implies that the algorithms within CardioDay® were tested against these reference databases, which constitutes a form of standalone performance evaluation. However, specific metrics, methodology, and results are not provided in this summary. The output of the device (ECG morphologies, graphs, statistical values) is then reviewed and edited by human users.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Given the mention of AHA and MIT databases, the ground truth for the algorithm evaluation would typically be expert annotations/consensus provided with these publicly available arrhythmia databases.
8. The sample size for the training set
The document does not provide any information about the sample size used for a training set. As a rule-based or conventional signal processing software (not explicitly stated as AI/machine learning), it might not have a "training set" in the modern sense. If it did employ machine learning, this detail is omitted.
9. How the ground truth for the training set was established
Not applicable, as no training set information is provided. If the algorithms were trained, the ground truth would likely be derived from expert annotations, similar to the test set ground truth.
§ 870.1425 Programmable diagnostic computer.
(a)
Identification. A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.(b)
Classification. Class II (performance standards).